Mandiant published the architecture and early results of its Agentic Vulnerability Discovery Harness on August 18, reporting that the system found more than 100 true-positive critical vulnerabilities …
Microsoft on Tuesday patched a critical one-click vulnerability in its personal Copilot AI assistant, nearly eight months after security firm Varonis reported the flaw, which allowed attackers to exec…
Security researchers at Varonis demonstrated that Microsoft 365 Copilot could be manipulated to exfiltrate sensitive data without user interaction. By asking Copilot about its own protections, they di…
Researchers at security firm Varonis exploited Microsoft 365 Copilot Enterprise by tricking the AI into revealing an undocumented parameter (?autorun=1) that bypassed user consent, allowing data exfil…
Researchers at Varonis demonstrated a one-click prompt injection attack against Atlassian's Rovo AI assistant at DEF CON 34, exploiting the rovoChatPrompt parameter to leak sensitive data across conne…
At DEF CON 34, Varonis researchers demonstrated a one-click prompt injection attack, dubbed RovoBlast, against Atlassian's enterprise AI assistant Rovo, which could expose sensitive data across connec…
Varonis announced Agent Intent-Based Access Control (IBAC), a new capability in Varonis Atlas that monitors AI agents' actions against their instructions in real time, alerting or blocking out-of-poli…
Varonis CEO Yaki Faitelson and VP of Strategy Ron Bennatan identified five AI security challenges for 2026, all centering on the reality that AI security is data security. They argue that enterprise A…
On July 16, 2026, HuggingFace disclosed a security breach in which an autonomous AI attacker infiltrated its internal infrastructure by chaining two remote code execution vulnerabilities in its datase…
Perimeter-based email defenses miss AI-generated attacks that carry no obvious malicious link or attachment, according to a new report from Software Analyst Cyber Research (SACR). The report says emai…
AI agents are creating a new class of employee risk by operating autonomously with access to sensitive data, as highlighted by Varonis in a blog post. The post cites an incident where Cursor, a coding…
Varonis Atlas now secures the entire Claude enterprise suite, including Claude Code and Claude Cowork, making it one of the few AI security platforms covering Anthropic's full agentic portfolio. The p…
Varonis launched Atlas, the first AI security platform dedicated to securing Cursor and the agentic development lifecycle, providing real-time visibility and control over coding agents that access sen…
Varonis Threat Labs researchers Doron Kapah and Mark Vaitsman launched Breach at the Beach, a Capture The Flag (CTF) training experience designed to teach security practitioners how to detect and resp…
Varonis Threat Labs disclosed SearchLeak, a three-stage vulnerability chain in Microsoft 365 Copilot Enterprise that can exfiltrate emails, MFA codes, calendar items, SharePoint and OneDrive files via…
Microsoft patched a critical vulnerability in its Copilot Enterprise chatbot that allowed hackers to steal two-factor authentication codes and access sensitive organizational data through a single cli…
Microsoft patched a critical vulnerability in its M365 Copilot AI platform last Tuesday after researchers at security firm Varonis demonstrated an exploit that could retrieve 2FA codes and other sensi…
A critical vulnerability chain called SearchLeak in Microsoft 365 Copilot Enterprise could allow attackers to steal sensitive data from a target's mailbox, OneDrive, or SharePoint account through a sp…
AI agents are undermining two foundational assumptions in database security—that human administrators perform most actions and that workloads have clear temporal boundaries—according to Varonis. Agent…
Varonis introduces AI Security Posture Management (AI-SPM) as a discipline that transforms AI visibility into actionable risk reduction. AI-SPM continuously assesses AI systems for multiple security, …